New methods reduce bias in estimating optimality gaps for risk-averse stochastic programs.
problem Optimality gap estimation bias in risk-averse stochastic programs.
method Two independent samples, each estimating a different component of the optimality gap.
result Our method reduces bias in estimating optimality gaps for risk-averse problems.
Random hyperbolic surfaces have nearly optimal spectral gaps.
problem Proving the nearly optimal spectral gap conjecture for random Belyi surfaces.
method Using the Brooks-Makover model, the authors show a spectral gap greater than 1/4 - c/log(n).
result A random hyperbolic surface in the Brooks-Makover model has a spectral gap greater than 1/4 - c/log(n).
New conditions prevent gaps in optimal control problems.
problem Preventing gaps in optimal control problems with state constraints.
method Developed new sufficient conditions not relying on convexity.
result Derived bounds for the size of the relaxation gap.
Study gap-dependent regret bounds for risk-sensitive RL.
problem Risk-sensitive reinforcement learning with entropic risk measure.
method Propose cascaded gaps to adapt to problem structures, derive regret bounds.
result Exponential improvement over existing bounds in appropriate settings.
Improved gap-dependent bounds for reinforcement learning with linear approximations.
problem Achieving nearly minimax-optimal performance with linear function approximation.
method Developed and analyzed the LSVI-UCB++ algorithm and its concurrent variant.
result First gap-dependent regret bound for nearly minimax-optimal algorithm LSVI-UCB++.
GNA optimally identifies the best arm with small gaps.
problem Best arm identification in fixed-budget settings.
method Generalized Neyman Allocation (GNA) for asymptotically locally minimax optimal BAI.
result GNA's worst-case bounds match the lower and upper bounds in the small-gap regime.
Study shows optimal spectral gaps diminish in large genus surfaces.
problem Optimizing spectral gaps in large genus surfaces.
method Analysis of Weil-Petersson probability and eigenvalues of Laplacian.
result Probability of optimal spectral gaps vanishes as genus increases.
Free adversarial training reduces the generalization gap compared to vanilla method.
problem Improving generalization in adversarial training.
method Analysis of algorithmic stability in free adversarial training.
result Free adversarial training shows a lower generalization gap.
Counterexample shows state-constrained optimal control problems can have Young measure gaps.
problem Existence of Young measure gaps in state-constrained optimal control problems.
method Provided a counterexample for smooth controllable systems state-constrained to the unit ball.
result Gap occurs in a regular setting with non-convex Lagrangian density.
We present a data-driven framework called generative adversarial privacy (GAP). Inspired by recent advancements in generative adversarial networks (GANs), GAP allows the data holder to learn the privatization mechanism directly from the data. Under GAP, finding the optimal privacy mechanism is formulated as a constrain…
Rewiring GNNs to optimize community and feature alignment improves their performance.
problem Improving GNNs' performance by addressing over-squashing and generalization issues.
method Three rewiring strategies: ComMa, FeaSt, and ComFy, targeting community structure, node labels, and their alignment.
result Rewiring strategies enhance GNNs' performance by optimizing label-community alignment.
Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.
problem Effective learning in linear bandits with corrupted rewards across different corruption models.
method Unified framework for analyzing strong and weak corruption, connection to gap-dependent misspecification, and specialized algorithm.
result Optimal bounds for gap-dependent misspecification in linear bandits.
Graph partitioning is the problem of dividing the nodes of a graph into balanced partitions while minimizing the edge cut across the partitions. Due to its combinatorial nature, many approximate solutions have been developed, including variants of multi-level methods and spectral clustering. We propose GAP, a Generaliz…
Optimal strategy found for identifying best arm in bandits with small gap.
problem Best arm identification in two-armed bandits with a fixed budget and small gap.
method Neyman allocation rule augmented with inverse probability weighting.
result Proposed strategy is asymptotically optimal when gap is small.
Corrects gaps in a method for optimizing high-frequency trading strategies.
problem Optimizing bid and ask limit order strategies in high-frequency trading.
method Uses an approximation method based on Avellaneda and Stoikov's 2008 article, correcting gaps found in it.
result The main answer in Avellaneda and Stoikov's article remains unchanged despite corrections.
GSP improves global average pooling for deep metric learning by learning weights and selecting semantic entities.
problem Improving global average pooling for deep metric learning.
method Generalized Sum Pooling (GSP) method that learns weights and selects semantic entities.
result GSP improves metric learning performance on 4 popular benchmarks.
Algorithm reduces regret in misspecified linear contextual bandits.
problem Misspecified linear contextual bandits with bounded misspecification.
method Data selection scheme for online regression, leveraging uncertainty.
result Regret bound of O ~ ( d 2 / Δ ) \tilde O(d^2/Δ) O ~ ( d 2 /Δ ) when ζ ≤ O ~ ( Δ / d ) ζ \leq \tilde O(Δ/\sqrt{d}) ζ ≤ O ~ ( Δ/ d ) . Logarithmic regret achieved in Q-learning with positive gap.
problem Achieving logarithmic cumulative regret in Q-learning with positive sub-optimality gap.
method Optimistic Q-learning with logarithmic regret bound.
result Logarithmic cumulative regret bound proven for optimistic Q-learning.
We study the gap between the state pension provided by the Italian pension system pre-Dini reform and post-Dini reform. The goal is to fill the gap between the old and the new pension by joining a defined contribution pension scheme and adopting an optimal investment strategy that is target-based. We find that it is po…
Survey on spectral gaps of random hyperbolic surfaces.
problem Understanding spectral gaps of random hyperbolic surfaces.
method Brief survey on geometry and spectra, discussion of results by Hide-Magee, Anantharaman-Monk, and Hide-Macera-Thomas.
result Near optimal spectral gaps for random surfaces.
Optimal privacy-preserving algorithm for solving saddle point problems.
problem Solving convex-concave stochastic saddle point problems under differential privacy constraints.
method Recursive regularization technique repurposed for saddle point problems, achieving strong gap rate of O(1/√n + √d/nε).
result Achieves nearly optimal strong gap rate of O(1/√n + √d/nε) with gradient complexity O(min{n^2ε^(1.5)/√d, n^(3/2)}).
Logarithmic regret achieved in RL with linear function approximation.
problem Achieving logarithmic regret in reinforcement learning with linear function approximation.
method LSVI-UCB for linear MDP assumption, UCRL-VTR for linear mixture MDP assumption.
result Logarithmic regret bounds established for RL with linear function approximation.
We suggest a general oracle-based framework that captures different parallel stochastic optimization settings described by a dependency graph, and derive generic lower bounds in terms of this graph. We then use the framework and derive lower bounds for several specific parallel optimization settings, including delayed …
New analysis improves understanding of bilevel optimization stability and generalization.
problem Understanding how well bilevel optimization algorithms generalize.
method Algorithmic stability arguments and generalization bounds for three bilevel minimax solvers.
result Precise trade-off between algorithmic stability, generalization gaps, and practical settings.
New study on neural network calibration, linking it to generalization gap.
problem Neural networks lack strong guarantees on calibration.
method Decomposed calibration error into train set and generalization gap.
result Models with small generalization gap are well-calibrated.
DGKIP extends KIP for dataset distillation without bi-level optimization.
problem Efficiently distill datasets for various loss functions.
method Leverages duality theory to avoid bi-level optimization.
result DGKIP supports a wider range of loss functions.
The paper proposes a method to test properties of the optimal assortment in multinomial logit models.
problem Uncertainty quantification for the optimal assortment in multinomial logit models.
method The paper proposes a novel inferential framework to test properties of the optimal assortment in multinomial logit models, reducing the problem to detecting the sign change point of marginal revenue gaps.
result The asymptotic normality of the marginal revenue gap estimator and the construction of a maximum statistic to detect the sign change point.
MAML optimizes shared priors for subtasks in a nonconvex meta-objective.
problem Understanding global optimality of MAML for nonconvex meta-objectives.
method Characterizes optimality gap of MAML stationary points via first-order optimization methods.
result Establishes global optimality of MAML for both RL and supervised learning.
New algorithm reduces sample complexity for planning in MDPs.
problem Planning in MDPs with unknown transitions.
method MDP-GapE, a trajectory-based MCTS algorithm.
result Proves upper bound on sample complexity in terms of sub-optimality gaps.
A new algorithm COVA-FC improves subgroup-fair clustering efficiency.
problem Challenges in making cluster assignments independent of sensitive attributes in subgroups.
method Defining a subgroup-fairness gap, deriving a covariance-based surrogate, and introducing a continuous relaxation for efficient optimization.
result COVA-FC achieves competitive cost-fairness trade-offs and improves computational efficiency.
New algorithm reduces regret in private online learning with optimal gap-dependent rate.
problem Optimal gap-dependent regret rate for private stochastic decision-theoretic online learning.
method Horizon-free pure-DP algorithm with exponential block partitioning and softmax selection.
result Explicit regret bound of 1000 ⋅ ( log K Δ min + log K ε ) 1000 \cdot (\frac{\log K}{Δ_{\min}}+\frac{\log K}{\varepsilon}) 1000 ⋅ ( Δ m i n l o g K + ε l o g K ) . New algorithm closes empirical gap in PFSGD performance.
problem Empirical performance gap between tuned SGD and PFSGD.
method Parameter-free algorithm based on Coin-Betting ODE updates.
result New algorithm outperforms tuned baselines and matches optimal performance.
New algorithm reduces RL policy optimization gap.
problem Insufficient theoretical understanding of policy optimization methods.
method Reference-based Policy Optimization with Stable at Any Time guarantee (RPO-SAT)
result Achieves nearly minimax optimal policy-based algorithm for tabular RL.
Study analyzes symmetric two-armed Bernoulli bandit problem with zero mean gap.
problem Analyzing symmetric two-armed Bernoulli bandit problem with zero mean gap.
method Associated with a solution of a linear heat equation, compute leading order terms of minmax optimal regret and pseudoregret.
result Explicitly compute leading order terms in three scaling regimes for the gap.
New offline RL method works with limited data and function approximators.
problem Sample efficiency with limited data and weak function approximators.
method Pessimistic algorithm based on version space formed by marginalized importance sampling (MIS), with gap assumption.
result Guarantees sample efficiency for simple algorithm under specific assumptions.
Random covers of hyperbolic surfaces have a spectral gap with polynomial rate.
problem Finding spectral gaps in random covers of hyperbolic surfaces.
method Applying recent work on spectral gaps to uniformly random covers of closed hyperbolic surfaces.
result Uniformly random degree-n covers of a closed hyperbolic surface have no new Laplacian eigenvalues below a specific threshold with high probability.
Investigates optimal PPI strategies in jump-diffusion models to mitigate downside risk.
problem Gap risk in PPI strategies due to jumps in asset price dynamics.
method Optimization problem with S-shaped utility functions, solved via martingale approach in a jump-diffusion framework.
result Determines optimal PPI strategy to maximize expected utility of terminal wealth.
There is a gap in the proof of the main theorem in the article [ShCh13a] on optimal bounds for the Morse lemma in Gromov-hyperbolic spaces. We correct this gap, showing that the main theorem of [ShCh13a] is correct. We also describe a computer certification of this result.
Study best arm identification with contextual info, achieving optimal misidentification probability.
problem Identify the best treatment arm with minimal misidentification probability in a small gap scenario.
method Developed RS-AIPW strategy that matches lower bound of misidentification probability in the small-gap regime.
result RS-AIPW strategy is asymptotically optimal for best arm identification.
New method uses model's generalization gap to predict membership inference attacks.
problem Predicting membership inference attacks on machine learning models.
method Uses the model's generalization gap as a metric to estimate the vulnerability to membership inference attacks.
result Demonstrates that the model's generalization gap provides an upper bound on MIA security.
The study proves optimal spectral gaps for hyperbolic surfaces.
problem Proving optimal spectral gaps for hyperbolic surfaces.
method Proving the absence of eigenvalues in a specific range for random covers of hyperbolic surfaces.
result The first non-zero eigenvalue of the Laplacian on a sequence of closed hyperbolic surfaces tends to 1/4.
Unified hybrid RL algorithm improves online RL performance with offline data.
problem Improving reinforcement learning performance with limited online data.
method A unified hybrid RL algorithm combining offline and online data.
result Unified algorithm achieves state-of-the-art results in sub-optimality gap and online learning regret.
Unified framework for CO problems using RL, providing optimal solutions and convergence guarantees.
problem Combinatorial optimization problems
method Unified framework of Markov decision processes (MDPs) and value-based reinforcement learning (RL) techniques
result RL techniques converge to approximate solutions with a guarantee on optimality gap
Game-theoretic analysis of mining gaps in blockchain systems.
problem Strategic mining behavior and its impact on blockchain stability.
method Game-theoretic model and Nash equilibrium analysis.
result Mining gaps can destabilize blockchain systems, especially with decreasing block rewards.
Paper tackles fast convergence for non-convex strongly-concave min-max problems.
problem Non-convex strongly-concave min-max problems in deep learning.
method Proximal stage-based method with PL condition for faster convergence.
result Established fast convergence in primal objective gap and duality gap.
In this paper, we focus on the problem of stochastic optimization where the objective function can be written as an expectation function over a closed convex set. We also consider multiple expectation constraints which restrict the domain of the problem. We extend the cooperative stochastic approximation algorithm from…
New study shows exponential lower bound for RL even with constant suboptimality gap.
problem Can RL be sample-efficient with a constant suboptimality gap?
method Analyzes reinforcement learning in the online setting with a linearly realizable optimal Q-function.
result An exponential sample complexity lower bound still holds even with a constant suboptimality gap.
UCB algorithm's arm-sampling behavior is revealed, leading to new insights and proofs.
problem Optimizing multi-armed bandit algorithms for worst-case scenarios.
method Analysis of UCB algorithm's arm-sampling behavior and process-level characterization.
result UCB's arm-sampling rates are asymptotically deterministic, regardless of problem complexity.